Comments (4)
1.Does this mean to train the network in a coarse-to-fine process, which initals the network from 256x256 and then finetunes it on larger sizes?
Yes
2.Does this accelerate the converge of the network than train it on size 736x736 directly?
Yes, because direct training on size 736 is very slow
my own training method:
set cfg.train_task_id = '2T256'
set patience 5(between 2~6)
python preprocess.py && python label.py && python advanced_east.py
when end of training, copy the best saved weights file(.h5) to initials the training of size 384, modify cfg.train_task_id = '2T384' and cfg.initial_epoch="the ending epoch" and cfg.load_weights=True and continue train.
then train 512 and so on. You could try this method, maybe there are better ways.
from advancedeast.
@huoyijie whether the network still remembers what they learned in 256 while training 736?
from advancedeast.
Hi,
I download tianchi ICPR dataset,set cfg.train_task_id = '3T256',run python3 preprocess.py && python3 label.py && python3 advanced_east.py. But I get this error. The output information is shown below. How can I fix this error? Can you help me?@LucyLu-LX @huoyijie @hcnhatnam
Epoch 00008: val_loss improved from 0.43569 to 0.42750, saving model to model/weights_3T256.008-0.427.h5
Epoch 9/24
1125/1125 [==============================] - 157s 139ms/step - loss: 0.2762 - val_loss: 0.4373
Epoch 00009: val_loss did not improve from 0.42750
Epoch 10/24
1125/1125 [==============================] - 156s 139ms/step - loss: 0.2579 - val_loss: 0.4435
Epoch 00010: val_loss did not improve from 0.42750
Epoch 11/24
1125/1125 [==============================] - 156s 139ms/step - loss: 0.2466 - val_loss: 0.4710
Epoch 00011: val_loss did not improve from 0.42750
Epoch 12/24
1125/1125 [==============================] - 156s 139ms/step - loss: 0.2342 - val_loss: 0.4633
Epoch 00012: val_loss did not improve from 0.42750
Epoch 13/24
1125/1125 [==============================] - 156s 139ms/step - loss: 0.2228 - val_loss: 0.4724
Epoch 00013: val_loss did not improve from 0.42750
Epoch 00013: early stopping
from advancedeast.
@globalmaster it isn't error. The training is stopped early(early stopping) to avoid overfit. Looks like the model is not converging and this is still my problem. @globalmaster, Can you share for me dataset with google driver link?
from advancedeast.
Related Issues (20)
- > 请问训练的时候缺少icpr/train_3T736.txt 怎么解决的??? HOT 3
- How to use EAST train a multiclass dataset
- 你好,请问在对点集找出13和24后,还需要对13和24的斜率进行比较,并换掉13和24的顺序?
- 为什么没有出现我的数据集没有出现_predict.jpg这样的图片,
- About time of prediction
- Can the model recognize the text content? Not just the position of the text
- 评价指标 HOT 1
- ValueError: output of generator should be a tuple `(x, y, sample_weight)` or `(x, y)`. Found: None
- 检测后识别 HOT 3
- 训练可视化
- > 你的检测结果是好的吗,为什么我的检测结果很差,可以邮件交流吗?[[email protected]](mailto:[email protected])
- 有没有keras.save()保存的模型,我想移植道Android端
- act.jpg中对文本进行了标注,predict.jpg由于缺少头尾部无法画出检测框
- utils.np_box_ops
- 有测试集的评估代码吗? HOT 1
- 模型裁剪问题
- A scenario when this model is worse than original EAST
- 评估
- 模型训练过程为什么是从小尺度到大尺度呢,有没有什么依据呢
- 检测效果太差
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from advancedeast.